TopicNet: Semantic Graph-Guided Topic Discovery
Authors: Zhibin Duan, Yi.shi Xu, Bo Chen, dongsheng wang, Chaojie Wang, Mingyuan Zhou
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on widely used benchmarks show that Topic Net outperforms related deep topic models on discovering deeper interpretable topics and mining better document representations. |
| Researcher Affiliation | Academia | Zhibin Duan, Yishi Xu, Bo Chen , Dongsheng Wang, Chaojie Wang National Laboratory of Radar Signal Processing, Xidian University, Xi an, China xd_zhibin@163.com, bchen@mail.xidian.edu.cn Mingyuan Zhou Mc Combs School of Business, The University of Texas at Austin mingyuan.zhou@mccombs.utexas.edu |
| Pseudocode | No | The paper does not contain any sections or figures explicitly labeled as 'Pseudocode' or 'Algorithm'. |
| Open Source Code | Yes | Our code is available at https://github.com/Bo Chen Group/Topic Net. |
| Open Datasets | Yes | Our experiments are conducted on four widely-used benchmark datasets, including 20Newsgroups (20NG), Reuters Corpus Volume I (RCV1), Wikipedia (Wiki), and a subset of the Reuters-21578 dataset (R8), varying in scale and document length. |
| Dataset Splits | No | The paper specifies a train/test split ('randomly select 80% of the word tokens from each document to form a training matrix X, holding out the remaining 20% to form a testing matrix Y') but does not explicitly mention a validation set or split for hyperparameter tuning. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers, such as libraries or frameworks used in the implementation. |
| Experiment Setup | Yes | Note that, in our experiments, the hyper-parameters are set as m = 10.0 and β = 1.0. ... For a 15-layer model, the topic size from bottom to top is set as K = [256, 224, 192, 160, 128, 112, 96, 80, 64, 56, 48, 40, 32, 16, 8], and the detailed description can be found in the Appendix. |